They are still big state-machines, unlike the human brain.
> They are still big state-machines, unlike the human brain.
The human brain can also be captured by a big state machine. See the Bekenstein Bound.
Theory of Mind May Have Spontaneously Emerged in Large Language Models
261–270 of 321 posts
Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models
#262Earlier quoted context omitted.
The whole point of this conversation is whether talking like an agent that has a theory of mind and actually having a theory of mind are the same thing. I responded to a thread about what "knowing" is, and the same distinction can apply. You're responding with "if it talks like it knows what a cat is, it must know what a cat is", and that's totally begging the question.
But that all boils down to are we having a scientific conversation or a philosophical conversation? In my opinion the only useful conversation is a scientific on. A philosophical conversation will and can never be resolved so if of no importance to this discussion. We can use philosophy to help guide our scientific conversation, but in the end only a scientific conversation can be helpful in reaching a meaningful/pra…
I think you're making a strawman to argue against. Nowhere above have I claimed that "knowing" requires "consciousness", or "it must be implemented identically to me to count", and in fact I believe neither.
But:
- In this context, following on the whole 2nd half of the 20th century where cognitive science and psychology moved past behaviorism and sought explanations of the _mechanisms_ underlying mental phenomena, a scientific discussion doesn't have to restrict itself to only considering what the LLM says. Neither we, nor the LLM are black boxes. Evidence of _how_ we do what we do is part of scientific inquiry.
- But the LLM does _not_ reproduce all the behaviors of an agent with a theory of mind. A two year-old with a developing theory of mind may try to hide food they don't want to eat. A 4-year-old playing hide-and-seek picks locations where they think their play-partner won't look. They take _actions_ which are appropriate for their goals and context which require consideration of the goals of others. The LLM shows elaborate behaviors in one dimension, in which it has been extensively trained. It has no capacity to do anything else, or even receive exposure to non-linguistic contexts.
I am in no way arguing that only meat-based minds can "know". I'm saying that the data, training regime and model structure used for LLMs specifically is extremely impoverished, in that we show it language but no other representation of the things language refers to. Similarly, image-generating AIs know what images look like, but they don't know how bodies or physical objects interact, because they have never been exposed to them. Of _course_ we get LLMs that hallucinate and image-generators that produce messed up bodies.
On the other hand, there are some pretty cool reinforcement-learning results where agents show what looks like cooperation, develop adversarial strategies, etc. There's experiments where software agents collaboratively invent a language to refer to objects in their (virtual) environment to accomplish simple tasks. I think there are a lot of near and medium-term possibilities coming from multi-modal models (i.e. can models trained on related text, images, audio, video) and RL which could yield knowledge of a kind that LLMs simply do not have.
Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models
#263Earlier quoted context omitted.
Two models having a coherent conversation - a scenario which follows directly from my post - would be a purely textual example of what I mean. > Perhaps we will never find out if language models have a theory of mind. We appear to be in agreement here. When the state of our knowledge is 'maybe', it seems rash to assume either 'yes' or 'no'.
What does it change when you add another model? I don't see how this lets us extract extra information. What distinguishes two conjoined models from one model with a narrowing across the middle? If the idea is to have two similar minds building a theory of each other, then I guess this could be informative, but first we'd have to establish that the models are "minds" in the first place. It's not clear to me what that…
Here's where I am coming from: there have been a number of experiments to teach language to other species, but there is always a problem in trying to figure out to what extent they 'get' language - For example, there is the case of the chimpanzee Washoe signing "water" and "bird" on first seeing a swan - was it, as some people contended, inventing a new phrase for picking out swans (or even aquatic birds in general), or was it merely making the signs for two different things in the scene before it? [1]
One thing that has not been seen (as far as I know) is two or more of these animal subjects routinely having meaningful conversations among themselves. This would be a much richer source of data, and I do not think it would leave much doubt that they 'got' language to a very significant degree.
[1] https://www.nybooks.com/articles/2011/11/24/can-chimps-conve...
Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models
#264Earlier quoted context omitted.
The question of grounding is a problem that arises in thinking about cognition in general, yes. In AI, it changes from a theoretical problem to a practical one, as this whole discussion proves. As for one-shot learning, what I was driving at, is that a truly intelligent system should not need to consume millions of documents in order to predict that, say, driving at night puts larger demands on one's vision than driv…
Why do you believe that a system should not need to consume millions of documents in order to be able to make predictions? For your example, the concepts of driving, night, vision, all need to be clearly understood, as well as how they relate to each other. The idea of 'common sense' is a good example of something which takes years to develop in humans, and develops to varying extents (although driving at night vs at…
I was thinking in terms of simple logic and semantics. The example I picked though muddied the waters by bringing in real-world phenomena. A better test would be anything that stays strictly within the symbolic world - the true umwelt of the language model. So, anything mathematical. After seeing countless examples of addition and documents discussing addition and procedures of addition, many order of magnitude more than a child ever gets to see when learning to add, still LLMs cannot do it properly. That, to me, is conclusive.
Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models
#265From a Nondualist perspective, the idea of consciousness being limited to certain entities and not others is based on the dualistic notion that there is a distinction between subject and object, self and other. Nondualism asserts that there is no fundamental difference between self and other, and that all apparent dualities are merely expressions of the underlying unity of pure consciousness.
In this context, the question of whether AI can become conscious is somewhat moot, as the Nondualist perspective holds that consciousness is not something that can be possessed by one entity and not another, but rather it is the underlying essence of all things. From this perspective, AI would not be becoming conscious, but rather expressing the consciousness that is already present in all things.
Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models
#266Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models
#267Earlier quoted context omitted.
Why do you believe that a system should not need to consume millions of documents in order to be able to make predictions? For your example, the concepts of driving, night, vision, all need to be clearly understood, as well as how they relate to each other. The idea of 'common sense' is a good example of something which takes years to develop in humans, and develops to varying extents (although driving at night vs at…
I was thinking in terms of simple logic and semantics. The example I picked though muddied the waters by bringing in real-world phenomena. A better test would be anything that stays strictly within the symbolic world - the true umwelt of the language model. So, anything mathematical. After seeing countless examples of addition and documents discussing addition and procedures of addition, many order of magnitude more…
A child can 'see' maths though, they can see that if you have one apple over here and one orange over there, then you have two pieces of fruit all together.
If you only ever allowed a child to read about adding, without ever being able to physically experiment with putting pieces together and counting them, likely children would not be able to add either.
In fact, many teachers and schools teach children to add using blocks and physical manipulation of objects, not by giving countless examples and documents discussing addition and procedures of addition.
You may feel it's conclusive, and it's your right to think that. I am not sure.
Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models
#268Earlier quoted context omitted.
Any specific part of it?
You can just read this review instead of the book: https://slatestarcodex.com/2020/06/01/book-review-origin-of-...
This does seem to be a pretty good summary, and also includes what seem to be the most major criticisms of the work.
Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models
#269This highlights one of the types of muddled thinking around LLMs. These tasks are used to test theory of mind because for people, language is a reliable representation of what type of thoughts are going on in the person's mind. In the case of an LLM the language generated doesn't have the same relationship to reality as it does for a person. What is being demonstrated in the article is that given billions of tokens o…
It's called Chinese Room: https://en.wikipedia.org/wiki/Chinese_room
> The question Searle wants to answer is this: does the machine literally "understand" Chinese? Or is it merely simulating the ability to understand Chinese?
To me: If you can't tell, it effectively doesn't matter.
Re: Theory of Mind May Have Spontaneously Emerged in Large Language Models
#270This highlights one of the types of muddled thinking around LLMs. These tasks are used to test theory of mind because for people, language is a reliable representation of what type of thoughts are going on in the person's mind. In the case of an LLM the language generated doesn't have the same relationship to reality as it does for a person. What is being demonstrated in the article is that given billions of tokens o…
> language is a reliable representation of what type of thoughts are going on in the person's mind
The wording used here inherently rejects Linguistic Determinism and, to a lesser extent, Linguistic Relativism.